基于BoBGSAL⁃Net的文档级实体关系抽取方法
|
|
冯超文, 吴瑞刚, 温绍杰, 刘英莉
|
Document⁃level entity relation extraction method based on BoBGSAL⁃NET
|
|
Chaowen Feng, Ruigang Wu, Shaojie Wen, Yingli Liu
|
|
表7 BoBGSAL?Net模型和其他模型在DocRED数据集上的实体抽取实验结果的对比
|
Table 7 Experimental results of entity extraction by BoBGSAL?Net and other model on the DocRED dataset
|
|
| 模型 | 验证集 | 测试 |
|---|
| Ign F1 | Ign AUC | F1 | AUC | Ign F1 | F1 |
|---|
| BoBGSAL⁃Net+BERT | 66.14% | 65.59% | 65.40% | 65.32% | 64.73% | 66.04% | | DocRED⁃CNN[32] | 40.27% | 32.75% | 43.35% | 34.17% | 36.44% | 42.33% | | MRN+BERT[33] | 59.47% | — | 60.20% | — | 59.52% | 61.74% | | DRN⁃GloVe[34] | 54.61% | — | 56.49% | — | 54.35% | 56.33% | | BoBGSAL⁃Net | 55.43% | 54.64% | 56.51% | 55.78% | 54.84% | 55.73% | | BoBGSAL⁃Net+GloVe | 60.45% | 56.47% | 59.29% | 57.89% | 57.57% | 59.14% | | BoBGSAL⁃Net+BiLSTM | 61.58% | 59.73% | 62.50% | 60.48% | 59.76% | 61.48% |
|
|
|